This model is a fine-tuned version of bert-base-cased on the article50v2_wikigold_split dataset. It achieves the following results on the evaluation set:

Loss: 0.5035
Precision: 0.4070
Recall: 0.0962
F1: 0.1556
Accuracy: 0.8049

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	20	0.6642	0.52	0.0063	0.0125	0.7816
No log	2.0	40	0.5316	0.3772	0.0630	0.1080	0.7974
No log	3.0	60	0.5035	0.4070	0.0962	0.1556	0.8049

Framework versions

Transformers 4.17.0
Pytorch 1.11.0+cu113
Datasets 2.4.0
Tokenizers 0.11.6

DOOGLAK/Article_50v2_NER_Model_3Epochs_AUGMENTED

Article_50v2_NER_Model_3Epochs_AUGMENTED

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

DOOGLAK/
Article_50v2_NER_Model_3Epochs_AUGMENTED